Find research datasets worth reusing

Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.

117

datasets available to search

ShareScore release 0.9.0

Dataset results

117 results for “Machine-learning”

Learn how ShareScore rates datasets ↗

zenodo52/100

Detecting repeating earthquakes on the San Andreas Fault with unsupervised machine-learning of spectrograms (supplementary material)

Supplementary material for Sawi et al., 2023, Detecting repeating earthquakes on the San Andreas Fault with unsupervised machine-learning of spectrograms (The Seismic Record). Catalog of repeating earthquakes in sequences on a 10-km long segment of the San Andreas Fault in California from 1984-2019.  Catalog HeaderYR/MO/DY...........Date of eventHR/MN/SC...........Time of eventLAT/LON/DEP........Location of eventEX/EY/EZ...........Relative location uncertainty (in m)MAG................NCSN magnitudeevID.................NCSN event IDseqID................Repeating earthquake sequence IDisRESp............Is quasi-periodic RES (bool) References: Sawi T., Waldhauser F., Holtzman B. K., Groebner, N. (2023) Detecting repeating earthquakes on the San Andreas Fault with unsupervised machine-learning of spectrograms. The Seismic Record. Waldhauser, F., and Schaff, D. P. (2021). A Comprehensive Search for Repeating Earthquakes in Northern California: Implications for Fault Creep, Slip Rates, Slip Partitioning, and Transient Stress. J Geophys Res B Solid Earth, 126(11), 1–22. <a href="https://doi.org/10.1029/2021JB022495">https://doi.org/10.1029/2021JB022495</a>

opencc-by-4.0Dec 2023View details →

zenodo48/100

A large data-set of CASP protein refinement simulations for machine-learning

The uploaded trajectory data originates from our own laboratory's refinement method in CASP11 and CASP12 for which the reference crystal structure is available in the PDB. In total the trajectory data consists of  904 trajectories with 3419 ns cumulative simulation time and 1,709,704 snapshots with a delta t =2 ps from 42 different protein systems. File Overview <ul> <li>trajectory_data_pdbs.tar.gz : contains the PDB files of the different trajectories as well as the starting model and reference crystal structure for each target</li> <li>casp_normalized_all_data_final.csv.gz :  contains the trajectory features calculated for each snapshot from the trajectory PDBs</li> <li>cv_folds.csv : contains the 7 fold cross-validation assignment used to assess the performance of the model  </li> </ul>

opencc-by-4.0Feb 2018View details →

zenodo48/100

Improving machine-learning models in materials science through large datasets

1. Image of the <a href="https://alexandria.icams.rub.de/">Alexandria database </a> state corresponding to the paper "Improving machine-learning models in materials science through large datasets". <ul> <li>Static pbe calculations for 1D, 2D, 3D compounds can be found in 1D_pbe.tar.gz, 2D_pbe.tar.gz, 3D_pbe.tar.gz in batches of 100k materials. The latter also contains a separate convex hull pickle with all compounds on the pbe convex hull (convex_hull_pbe_2023.12.29.json.bz2) and a list of prototypes in the database (prototypes.json.bz2). The systematic 3D calculations performed for the article Improving machine-learning models in materials science through large datasets (in the paper referred to as round 2 and 3) can be found by the location keyword in the data dictionary of each ComputedStructureEntry containing  "cgat_comp/quaternaries" (round 2) and "cgat_comp2/"  (round 3).  Round 1 (10.1002/adma.202210788) can be found under "cgat_comp/ternaries", ""cgat_comp/binaries".</li> <li>Static pbesol calculations for 3D compounds can be found in 3D_ps.tar (still zip compressed) in batches of 100k materials. The folder also contains a separate convex hull pickle with all compounds on the pbesol convex hull (convex_hull_ps_2023.12.29.json.bz2). </li> <li>Static scan calculations for 3D compounds can be found in 3D_scan.tar (still zip compressed) in batches of 100k materials. The folder also contains a separate convex hull pickle with all compounds on the scan convex hull (convex_hull_scan_2023.12.29.json.bz2). </li> <li>Geometry relaxation curves for 1D and 2D and 3D compounds calculated with PBE can be found in geo_opt_1D.tar.gz, geo_opt_2D.tar.gz. and geo_opt_3D.tar. Each file in each folder contains a batch of up to 10k relaxation trajectories.</li> <li>PBESOL relaxation trajectories for 3D compounds can be found in geo_opt_ps.tar</li> </ul> 2. Crystal graph attention networks to predict the volume (<a href="https://zenodo.org/api/records/12582650/draft/files/volume_round_3.tar.gz/content" target="_blank" rel="noopener noreferrer">volume_round_3.tar.gz</a>) and distance to the convex hull (<a href="https://zenodo.org/api/records/12582650/draft/files/e_above_hull_round_3.tar.gz/content" target="_blank" rel="noopener noreferrer">e_above_hull_round_3.tar.gz</a>) trained for the paper "Improving machine-learning models in materials science through large datasets". Can be used with the code at https://github.com/hyllios/CGAT/tree/main/CGAT. Note will predict the distance to the convex hull not normalized per atom when using the code on the github. 3. Alignn models as well as m3gnet and mace models corresponding  to the publication can be found in <a href="https://zenodo.org/api/records/12582650/draft/files/alexandria_v2.tar.gz/content" target="_blank" rel="noopener noreferrer">alexandria_v2.tar.gz</a> 4. scripts.tar.gz Some scripts used for generating CGAT input data/ performing parallel predictions and for relaxations with m3gnet/mace force fields

opencc-by-4.0Sep 2024View details →

zenodo48/100

Toward a Generalizable Machine-Learned Potential for Metal-Organic Frameworks

<ul> <li>This repository contains the dataset used in the publication   `Toward Generalizable Machine Learned Potential for Metal-Organic Frameworks` Yue Yifei, Saad Aldin Mohammed, Loh Duane*, Jiang Jianwen*      Please each the README.md within each subfolder. For brevity, the data is organized into three sections      1. The dataset in DATASET       - The training and testing dataset, including structures of MOFs in extxyz format          2. The training output files and logs in NEQUIP-TRAIN       - The conda environment details, training scripts and logs       - Also Training and testing metrics in csv files      - This is split into two zip files NEQUIP-TRAIN1 and NEQUIP-TRAIN2 due to their size         3. Examples of using the developed models in MD simulations       - Including LAMMPS scripts, data file and environment details used in our scalability tests       - The complied Nequip-patched LAMMPS version is also provided       - Details on how to use our models - we used a default model that is slower but more accurate in our study but faster models are also developed.</li> </ul>

opencc-by-4.0Oct 2024View details →

zenodo44/100

TCOM-H2O: TOMCAT CTM and Occultation Measurements based daily zonal stratospheric H2O profile dataset [1991-2021] constructed using machine-learning.

Methodology:   The TOMCAT simulation was conducted at a T64L32 resolution, consistent with previous work by Dhomse et al. (2021, 2022), covering the period from 2000 to 2024. These simulations utilized ERA-5 reanalysis data. <h3>H2O Profile Processing and Bias Correction</h3> Collocated H2O profiles are organized into five distinct latitude bins: <ul> <li> NH polar: 90∘N - 50∘N </li> <li> NH mid-lat: 20∘N - 70∘N </li> <li> Tropics: 40∘S - 40∘N </li> <li> SH mid-lat: 70∘S - 20∘S </li> <li> SH polar: 90∘S - 50∘S </li> </ul> Initially, differences between TOMCAT and satellite measurements (primarily ACE-FTS data) are calculated for each zonal bin across 51 height levels (ranging from 10,km to 60,km). Note that TOMCAT may not accurately capture H2O evolution post-HTHH eruption due to the sparse spatial coverage of ACE measurements, which limits training data. Separate XGBoost regression models are then trained for these H2O differences at each height level within a given latitude bin. These trained models are subsequently used to estimate H2O bias corrections for all daytime TOMCAT grids (9132 days), specifically sampled at 1:30 PM local time at the equator. This yields grid-specific bias corrections that are applied to the original TOMCAT profiles. Height-resolved H2O profile data are then interpolated onto 28 standard pressure levels (from 300,hPa to 0.1,hPa), using pressure levels directly from the TOMCAT grids. For overlapping latitude bins, values are averaged to ensure smoother fields near boundary regions. We acknowledge the inherent dry biases in the original TOMCAT H2O profiles, largely because the TTL entry mixing ratios are based on a simplistic sinusoidal seasonal cycle, which omits the H2O enhancement contributed by tropical convective clouds. <h3>Data Files</h3> The dataset includes two files containing daily mean zonal mean H2O profiles: <ul> <li> <code>zmh2o_TCOM_hlev_T2Dz_2000-2024_V1.1.nc</code>: Contains height level data (10,km to 60,km). </li> <li> <code>zmh2o_TCOM_plev_T2Dz_2000-2024_V1.1.nc</code>: Contains pressure level data (300,hPa to 0.1,hPa). </li> </ul> <h3>Reference Publication</h3> This methodology, incorporating only ACE-FTS data and various minor algorithmic developments, is based on the following publication: Dhomse, S. S. and Chipperfield, M. P.: Using machine learning to construct TOMCAT model and occultation measurement-based stratospheric methane (TCOM-CH4) and nitrous oxide (TCOM-N2O) profile data sets, Earth Syst. Sci. Data, 15, 5105–5120, <a title="null" href="https://doi.org/10.5194/essd-15-5105-2023">https://doi.org/10.5194/essd-15-5105-2023</a>, 2023.

opencc-by-4.0May 2023View details →

zenodo44/100

TCOM-O3: TOMCAT CTM and Occultation Measurements based daily zonal stratospheric ozone profile dataset [1991-2021] constructed using machine-learning

Methodology:  TOMCAT simulation is performed at T64L32 resolution for the 2000-2024 time period. Collocated Ozone (O3) profiles are divided in five latitude bins: SH polar (90S-50S), SH mid-lat (70S-20S), tropics (40S-40N), NH mid-lat (20N-70N) and NH polar (50N-90N). Initially, model-measurement  differences are calculated for each zonal bins (51 height levels, 10km to 60km). Note that if enough ACE measurements are not avaliable for a particular level then data is purely based on TOMCAT simulated output field. Separate XGBoost regression models are trained for the  differences between TOMCAT and measurements at each level for a given latitude bin. XGBoost model is then used to estimate error corrections for all the TOMCAT grids.  TOMCAT output sampled at 1.30 pm local time at the equator. Estimated corrections for a given model grid that are added to the original TOMCAT simulated day and night time ozone profiles. Height resolved data are then interpolated on 28-pressure levels (300 - 0.1hPa). For overlapping latitude bins, we use averages and then calculate daily zonal mean values.  For more details see attached presentation. Previous version use both HALOE and ACE data. Here only ACE data is used (hence starting date is 01 January 2000). PDF file shows comparison between v1.0 and v1.1 as well as TOMCAT data. Dataset also includes two files containing daily mean zonal mean hydrogen fluoride  profiles on height (10-60 km) and pressure (300-0.1 hPa) levels: zmo3_TCOM_hlev_T2Dz_2000_2024.nc – height level data (10 to 60 km) zmo3_TCOM_plev_T2Dz_2000_2024.nc – pressure level data (300 to 0.1 hPa) Daily 3D profiles on height and pressure levels would be made available on request.

opencc-by-4.0Feb 2023View details →

zenodo44/100

Machine-Learning of Aerosol-Cloud-Climate Interactions Reveals an increased Cloud Fraction

Data presented in the manuscript "Machine-Learning of Aerosol-Cloud-Climate Interactions Reveals an increased Cloud Fraction" by Chen et al. (2022).

opencc-by-4.0Dec 2021View details →

zenodo44/100

Gaia EDR3 Catalogs of Machine-Learned Radial Velocities

Gaia EDR3 Catalogs of Machine-Learned Radial Velocities Spatially complete Test-Set and Machine-Learned Radial Velocity (ML-RV) Catalogs described in Dropulic et al., arXiv:<a href="https://arxiv.org/abs/2205.12278">2205.12278</a>. The spatially complete Test-Set Catalog contains a total of 4,332,657 stars, while the  spatially complete ML-RV Catalog contains 91,840,346 stars. We provide Gaia EDR3 Source IDs, the network-predicted line-of-sight velocity in km/s, and the network-predicted uncertainty in km/s.  We have included a simple Jupyter notebook demonstrating how to import the data, and make a simple histogram with it. If you find this catalog useful in your work, please cite Dropulic et al. arXiv:<a href="https://arxiv.org/abs/2205.12278">2205.12278</a>, as well as Dropulic et al. <a href="https://doi.org/10.3847/2041-8213/ac09ef">ApJL 915, L14 (2021)</a> arXiv:<a href="https://arxiv.org/abs/2103.14039">2103.14039</a>.

opencc-by-4.0May 2022View details →

zenodo44/100

Nonlocal machine-learned exchange functional for molecules and solids

This dataset supplements the journal article "Nonlocal machine-learned exchange functional for molecules and solids," published in Physical Review B: <a href="https://doi.org/10.1103/PhysRevB.110.075130">DOI:10.1103/PhysRevB.110.075130</a>. It contains the machine-learned functionals developed in the study (which can be used with the <a href="https://github.com/mir-group/CiderPressLite">CiderPressLite code</a>), along with additional data and results from the study. Please see the README.md file for more details on the dataset, and refer to the original paper for details on methodology and funding acknowledgments.

opencc-by-4.0Aug 2024View details →

zenodo44/100

Training Machine-Learned Density Functionals on Band Gaps

This dataset contains atomic structures and molecular orbitals (computed with DFT using the PBE functional) for the systems studied in the paper "<a href="https://doi.org/10.1021/acs.jctc.4c00999">Training Machine-Learned Density Functionals on Band Gaps</a>." The <a href="https://github.com/mir-group/CiderPress">CiderPress code</a> can be used to analyze the data. Please see the README.md file for more details on the dataset, and refer to the original paper for details on methodology and funding acknowledgments.

opencc-by-4.0Aug 2024View details →

zenodo44/100

Data and software: Heat flux for semi-local machine-learning potentials

This repository contains data, code, and related artefacts supporting the following publication: "Heat flux for semi-local machine-learning potentials" by Marcel F. Langer, Florian Knoop, Christian Carbogno, Matthias Scheffler, and Matthias Rupp arXiv: TBD doi: TBD   More details can be found in the main README.md file, and the README.md files in the subfolders. For any further questions, feel free to contact mail@marcel.science, @marceldotsci on Twitter, or @marcel@sigmoid.social.

opencc-by-4.0Dec 2022View details →

zenodo44/100

Machine-learning based lightning nowcasting data archive

This data archive contains the derived data supporting the findings of article "Lightning nowcasting with aerosol-informed machine learning and satellite-enriched dataset". The paper is currently in the preprint version:  https://doi.org/10.21203/rs.3.rs-2616886/v1 The prediction results in this data archive are generated by various models: 1. Current model. The model involves data input of aerosol observations together with meteorological variables and auxiliary datasets, as well as data enrichment by Geostationary Lightning Mapper (GLM). In the demo of the dataset, the year of 2020 is trained and predicted on a cross-validation scheme.  2. LMA model. The model acts as the baseline model considering only data label obtained from the ground-based Lightning Mapping Array (LMA), which observes accurate lightning occurrence in limited spatial range. 3. No-AOD model. The model acts as the baseline model considering no aerosol observation is utilized during the machine learning process.  The model results are demonstrated in a continuous value in 0-1. Trade-offs between Probability of Detection (POD) and False Alarm Ratio (FAR) can be optimized by selection of different thresholds.  Other datasets: 1. Dataset for training. It is for the public use of machine learning training for the current model and no-AOD model (training input features vary). 2. PM2.5 dataset. The real-time spatially continuous and hourly-level PM2.5 dataset is obtained following a published method by Zeng  et al.. In this method, the fundamental in-situ measurements are obtained from Air Quality System (AQS) monitoring network operated by United States Environmental Protection Agency. Reference: Siwei Li, Ge Song, Jia Xing et al. Lightning nowcasting with aerosol-informed machine learning and satellite-enriched dataset, 14 March 2023, PREPRINT (Version 1) available at Research Square [https://doi.org/10.21203/rs.3.rs-2616886/v1] Zeng, Z. et al. Estimating hourly surface PM2. 5 concentrations across China from high-density meteorological observations by machine learning. Atmospheric Research 254, 105516 (2021).

opencc-by-4.0Jul 2023View details →

zenodo40/100

XIS: A daily spatiotemporal machine-learning model for environmental exposures in the contiguous United States

These Parquet files contain the outputs used for many analyses and plots in the linked papers. For temperature and humidity, the full sets of observations for cross-validation aren't included because we used restricted-use MADIS data.

opencc-by-sa-4.0Jun 2023View details →

zenodo40/100

TCOM-CH4: TOMCAT CTM and Occultation Measurements based daily zonal stratospheric methane profile dataset [1991-2021] constructed using machine-learning

Methodology:   he TOMCAT simulation was conducted at a T64L32 resolution, consistent with previous work by Dhomse et al. (2021, 2022), covering the period from 2000 to 2024. These simulations utilized ERA-5 reanalysis data. <h3>CH4 Profile Processing and Bias Correction</h3> Collocated CH4 profiles are organized into five distinct latitude bins: <ul> <li> NH polar: 90∘N - 50∘N </li> <li> NH mid-lat: 20∘N - 70∘N </li> <li> Tropics: 40∘S - 40∘N </li> <li> SH mid-lat: 70∘S - 20∘S </li> <li> SH polar: 90∘S - 50∘S </li> </ul> Initially, differences between TOMCAT and satellite measurements (primarily ACE-FTS data) are calculated for each zonal bin across 51 height levels (ranging from 10,km to 60,km). It is important to note that unlike previous versions that might have used both HALOE and ACE measurements, this version exclusively utilizes ACE-FTS data, which is why the dataset starts from 2000. Separate XGBoost regression models are then trained for these CH4 differences at each height level within a given latitude bin. These trained models are subsequently used to estimate CH4 bias corrections for all daytime TOMCAT grids (9132 days), specifically sampled at 1:30 PM local time at the equator. This yields grid-specific bias corrections that are applied to the original TOMCAT profiles. Height-resolved CH4 profile data are then interpolated onto 28 standard pressure levels (from 300,hPa to 0.1,hPa), using pressure levels directly from the TOMCAT grids. For overlapping latitude bins, values are averaged to ensure smoother fields near boundary regions. <h3>Data Files</h3> The dataset includes two files containing daily mean zonal mean CH4 profiles: <ul> <li> <code>zmch4_TCOM_hlev_T2Dz_2000-2024_V1.1.nc</code>: Contains height level data (10,km to 60,km). </li> <li> <code>zmch4_TCOM_plev_T2Dz_2000-2024_V1.1.nc</code>: Contains pressure level data (300,hPa to 0.1,hPa). </li> </ul> <h3>Reference Publication</h3> This methodology, incorporating only ACE-FTS data and various minor algorithmic developments, is based on the following publication: Dhomse, S. S. and Chipperfield, M. P.: Using machine learning to construct TOMCAT model and occultation measurement-based stratospheric methane (TCOM-CH4) and nitrous oxide (TCOM-N2O) profile data sets, Earth Syst. Sci. Data, 15, 5105–5120, <a title="null" href="https://doi.org/10.5194/essd-15-5105-2023">https://doi.org/10.5194/essd-15-5105-2023</a>, 2023.

opencc-by-4.0Nov 2022View details →

zenodo40/100

TCOM-N2O: TOMCAT CTM and Occultation Measurements based daily zonal stratospheric nitrous oxide profile dataset [1991-2021] constructed using machine-learning

Methodology:   The TOMCAT simulation was conducted at a T64L32 resolution, consistent with previous work by Dhomse et al. (2021, 2022), covering the period from 2000 to 2024. These simulations utilized ERA-5 reanalysis data. <h3>N2O Profile Processing and Bias Correction</h3> Collocated N2O profiles are organized into five distinct latitude bins: <ul> <li> NH polar: 90∘N - 50∘N </li> <li> NH mid-lat: 20∘N - 70∘N </li> <li> Tropics: 40∘S - 40∘N </li> <li> SH mid-lat: 70∘S - 20∘S </li> <li> SH polar: 90∘S - 50∘S </li> </ul> Initially, differences between TOMCAT and satellite measurements (primarily ACE-FTS data) are calculated for each zonal bin across 51 height levels (ranging from 10,km to 60,km). Separate XGBoost regression models are then trained for these N2O differences at each height level within a given latitude bin. These trained models are subsequently used to estimate N2O bias corrections for all daytime TOMCAT grids (9132 days), specifically sampled at 1:30 PM local time at the equator. This yields grid-specific bias corrections that are applied to the original TOMCAT profiles. Height-resolved N2O profile data are then interpolated onto 28 standard pressure levels (from 300,hPa to 0.1,hPa), using pressure levels directly from the TOMCAT grids. For overlapping latitude bins, values are averaged to ensure smoother fields near boundary regions. <h3>Data Files</h3> The dataset includes two files containing daily mean zonal mean N2O profiles: <ul> <li> <code>zmn2o_TCOM_hlev_T2Dz_2000-2024_V1.1.nc</code>: Contains height level data (10,km to 60,km). </li> <li> <code>zmn2o_TCOM_plev_T2Dz_2000-2024_V1.1.nc</code>: Contains pressure level data (300,hPa to 0.1,hPa). </li> </ul> <h3>Reference Publication</h3> This methodology, incorporating only ACE-FTS data and various minor algorithmic developments, is based on the following publication: Dhomse, S. S. and Chipperfield, M. P.: Using machine learning to construct TOMCAT model and occultation measurement-based stratospheric methane (TCOM-CH4) and nitrous oxide (TCOM-N2O) profile data sets, Earth Syst. Sci. Data, 15, 5105–5120, <a title="null" href="https://doi.org/10.5194/essd-15-5105-2023">https://doi.org/10.5194/essd-15-5105-2023</a>, 2023.

opencc-by-4.0Nov 2022View details →

zenodo40/100

Calibration-free reaction yield quantification by HPLC with a machine-learning model of extinction coefficients

This repository contains all the data and code associated with the manuscript "Calibration-free reaction yield quantification by HPLC with a machine-learning model of extinction coefficients" Mass spec and absorption chromatogram data are in reaction_set_1.zip, reaction_set_2.zip, and simulated_reaction_set.zip. The chemprop model trained on the Deep4Chem dataset is in Deep4Chem_chemprop.zip.

opencc-by-4.0Mar 2024View details →

zenodo40/100

Small dataset machine-learning approach for efficient design space exploration: engineering ZnTe-based high-entropy alloys for water splitting

Atomic structure data used in the research article entitled "Small Dataset Machine-Learning Approaches to Explore the Design Space of High-Entropy Alloys: Engineering ZnTe-based Multicomponent Alloys for the Photo-Splitting of Water"

opencc-by-4.0Apr 2024View details →

zenodo40/100

TocoDecoy: a new approach to design unbiased datasets for training and benchmarking machine-learning scoring functions

This dataset file contains TocoDecoy datasets generated based on the targets and active ligands of LIT-PCBA. 1_property_filtered.zip : <ul> <li>TD set: the ligand file name, 2D T-sne vectors, Smiles, molecular weight (MW), Wildman-Crippen partition coefficient (log P), number of rotatable bonds (RB), number of hydrogen-bond acceptors (HBA), number of hydrogen-bond donors (HBD), number of halogens (HAL), topology similarities of decoys to the seed active ligands, active label (active or inactive) and training set label (whether belongs to training set or test set) OF active ligands and their topologically dissimilar decoys</li> <li>CD set: the decoy conformations with low docking scores generated by docking active ligands into protein pockets using Glide, Schrödinger.</li> </ul>

opencc-by-4.0Aug 2021View details →

zenodo40/100

Molecular similarity perception based on machine-learning models

Molecular similarity is an particularly important notion for chemical legislation, specifically in the evaluation process for orphan drugs (i.e., drugs for rare diseases). A new molecule needs to be dissimilar from any other existing drug for a given disease to be assigned the financially advantageous status of orphan drug. Currently, there are many ways to define whether two molecules are similar or dissimilar. Thus far, the European Medicines Agency has used experts majority voting on discretional judgments of similarity when assessing new drugs for rare diseases. The decision of individual expert whether two compounds are similar is inherently subjective, depending on factors such as gender, age, state of mind, and previous experiences. It is therefore desirable, in this context, to benefit from an objective measure of similarity. To answer this need, we report a new dataset of molecular similarity assessments, that includes complex and difficult similarity scenarios. As a result, we propose new and improved models for similarity-prediction procedures, including 3D properties. These models are publicly available: <a href="https://chematlas.chimie.unistra.fr/ReadySim/">https://chematlas.chimie.unistra.fr/ReadySim/</a>. Software, 3D structures and pictures are available in the git related to this deposit: <a href="https://github.com/enricogandini/paper_similarity_prediction.git">https://github.com/enricogandini/paper_similarity_prediction.git</a> The deposit contains two files. <ul> <li>original_training_set.csv: this is one of the dataset published initially in [doi: 10.1186/1758-2946-6-5].</li> <li>new_dataset.csv: result from a new survey organized in 2020</li> </ul> The columns are the following: <ul> <li>id_pair: unique identifier of the compound pair</li> <li>curated_smiles_molecule_a: first compound of the pair</li> <li>curated_smiles_molecule_b: second compound of the pair</li> <li>tanimoto_cdk_Extended: ECFP similarity measure</li> <li>TanimotoCombo: ComboScore similarity measure</li> <li>pchembl_distance: difference of activity of the compound pair</li> <li>target_name: protein to which the compound pair is binding</li> <li>simil_2D: similar based on ECFP (0 or 1)</li> <li>simil_3D: similar based on ComboScore (0 or 1)</li> <li>dissimil_2D: dissimilar based on ECFP (0 or 1)</li> <li>dissimil_3D: dissimilar based on ComboScore (0 or 1)</li> <li>pair_type: pairs are classified based on ECFP and ComboScore as similar or dissimilar in 2D and 3D - Sim2DSim3D, Sim2DDis3D, Dis2D,Sim3D, Dis2DSim3D</li> <li>n_answers: number of answers from experts</li> <li>n_similar: number of answers labeling the pair as similar compounds</li> <li>frac_similar: n_similar/n_answers</li> </ul>

openmit-licenseApr 2022View details →

dryad40/100

Bee Tracker – an open-source machine-learning based video analysis software for the assessment of nesting and foraging performance of cavity-nesting solitary bees

The foraging and nesting performance of bees can provide important information on bee health and is of interest for risk and impact assessment of environmental stressors. While radio-frequency identification (RFID) technology is an efficient tool increasingly used for the collection of behavioral data in social bee species such as honey bees, behavioral studies on solitary bees still largely depend on direct observations, which is very time-consuming. Here, we present a novel automated methodological approach of individually and simultaneously tracking and analyzing foraging and nesting behavior of numerous cavity-nesting solitary bees. The approach consists of monitoring nesting units by video recording and automated analysis of videos by a machine learning based software. This Bee Tracker software consists of four trained deep learning networks to detect bees that enter or leave their nest and to recognize individual IDs on the bees' thorax as well as the IDs of their nests according to their positions in the nesting unit. The software is able to identify each nest of each individual nesting bee, which permits to measure individual-based measures of reproductive success. Moreover, the software quantifies the number of cavities a female enters until it finds its nest as a proxy of nest recognition, and it provides information on the number and duration of foraging trips. By training the software on 8 videos recording 24 nesting females per video, the software achieved a precision of 96% correct measurements of these parameters. The software could be adapted to various experimental setups by training it to an according set of videos. The presented method allows to efficiently collect large amounts of data on cavity-nesting solitary bee species and represents a promising new tool for the monitoring and assessment of behavior and reproductive success under laboratory, semi-field and field conditions.

opencc-zeroJan 2023View details →

ScienceDex guides

Understand access before you commit

These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.

Compare curated datasets

Allen Brain Atlas

Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.

allen-brain-atlas

neuroscienceopenDocumentation, web resources, and API references are available online.

Last verified 2026-04-30Open record

Annotated Behaviour and Observability Dataset (ABODe)

ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.

abode-home-cage

behavioral-neuroscienceopenThe DataShare record exposes download links for annotations, documentation, license text, and the zipped per-snippet data directory.

Last verified 2026-04-30Open record

DANDI Archive for NWB datasets

DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.

dandi-nwb

electrophysiologyopenPublished Dandiset metadata and archive endpoints are available through the production DANDI API.

Last verified 2026-04-30Open record

International Brain Laboratory public data

The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.

ibl

behavioral-neuroscienceopenPublic sessions can be searched and loaded from the IBL public data server through ONE.

Last verified 2026-04-29Open record

OpenNeuro

OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.

openneuro

neuroscienceopenPublished datasets are available on demand over the internet.

Last verified 2026-04-29Open record